• Journal of Information Science Theory and Practice
• /
• v.1 no.1
• /
• pp.10-26
• /
• 2013

Domain transfer is a widely recognized problem for machine learning algorithms because models built upon one data domain generally do not perform well in another data domain. This is especially a challenge for tasks such as opinion classification, which often has to deal with insufficient quantities of labeled data. This study investigates the feasibility of self-training in dealing with the domain transfer problem in opinion classification via leveraging labeled data in non-target data domain(s) and unlabeled data in the target-domain. Specifically, self-training is evaluated for effectiveness in sparse data situations and feasibility for domain adaptation in opinion classification. Three types of Web content are tested: edited news articles, semi-structured movie reviews, and the informal and unstructured content of the blogosphere. Findings of this study suggest that, when there are limited labeled data, self-training is a promising approach for opinion classification, although the contributions vary across data domains. Significant improvement was demonstrated for the most challenging data domain-the blogosphere-when a domain transfer-based self-training strategy was implemented.

• Journal of Digital Convergence
• /
• v.15 no.11
• /
• pp.425-432
• /
• 2017

The current recommendation systems have problems including the difficulty of figuring out whether they recommend items that actual users have preference for or have simple interest in, the scarcity of data to recommend proper items due to the extremely small number of users, and the cold-start issue of the dropping system performance to recommend items that can satisfy users according to the influx of new users. In an effort to solve these problems, this study implemented a movie recommendation system to ensure user satisfaction by using the Fuzzy-Analytic Hierarchy Process, which can reflect uncertain situations and problems, and the data partition algorithm to group similar items among the given ones. The data of a survey on movie preference with 61 users was applied to the system, and the results show that it solved the data scarcity problem based on the Fuzzy-AHP and recommended items fit for a user with the data partition algorithm even with the influx of new users. It is thought that research on the density-based clustering will be needed to filter out future noise data or outlier data.

• Korean Management Science Review
• /
• v.32 no.1
• /
• pp.133-145
• /
• 2015

Motion picture industry in Korea has been growing constantly and aroused various kinds of research attention. Particularly, the introduction of official box-office database service brought quantitative studies. However, approaches based on diffusion models have been rarely found with domestic film markets. In addition to the fundamental statistical review on Korea and US film markets, we applied a diffusion model to daily box-office revenue. Unlike conventional preference of Gamma distribution on the film markets, estimation results proved that BMIC can also explain the trend of daily revenue successfully. The comparison with BMIC showed that there is a distinctive difference in diffusion patterns of Korea and US film markets. Generally, word-of-mouth effect appeared more significant in Korea.

• International Journal of Contents
• /
• v.8 no.3
• /
• pp.94-99
• /
• 2012

Science fiction films touch coming-future themes, particularly those referring specifically to futuristic technology and its influence over human life. Dealing with the resistance of the replicants in the approaching millennium, Blade Runner brings the feat of modern civilization into doubt through the image of the dystopian future. In Blade Runner, a city is filled with waste, pollution, and dirt and a corrosive rain falls from the polluted clouds. Adorno criticizes contemporary society and its civilization. Characterizing advanced capitalist society by its total administration penetrating into every sphere of life, he contends that modern society promotes alienation, atomization, conformism, and fatalism. Blade Runner provides a chance to contemplate the problems of modern society, proposed by Adorno's critical works. Therefore, this paper attempts to analyze futuristic characteristics described in the film with Adorno's critique of modern society.

• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.1
• /
• pp.81.1-81.1
• /
• 2016

A total solar eclipse occurs on March 9 along the path through Indonesia and the Pacific. KASI organized an expedition team for total solar eclipse observation. The main purpose of this observation is to test the coronal temperature and outflow velocity diagnostics based on filter observation, which is proposed for the next generation coronagraph. In addition, various white light observations including automatic programmed observation, manual observation, linear polarization, and time-lapse movie will be tried. We report the preliminary result of the expedition.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.10-12
• /
• 2003

Recommender systems help consumers to find the useful products from the overloaded information. Researchers have developed content-based recommenders, collaborative recommenders, and a few hybrid systems. In this research, we extend the classic collaborative recommenders by clustering method to form a hybrid recommender system. Using the clustering method, we can recommend the products based on not only the user ratings but also other useful information from user profiles or attributes of items. Through our experiments on well-known MovieLens data set, we found that the information provided by the attributes of item on the item-based collaborative filter shows advantage over the information provided by user profiles on the user-based collaborative filter.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.716-719
• /
• 2015

'영화 속에 등장하는 주연들은 어떤 기준으로 선정되는가'에서 본 논문에서는 두 가지 방법을 활용하여 주연들을 추출해보았다. 그 결과 가중치 연결 중심도를 이용한 검출 방법이 공식적인 주연급 등장인물과 일치한다는 것을 도출해냄.

• Journal of The Korean Association For Science Education
• /
• v.28 no.7
• /
• pp.768-778
• /
• 2008

The most important factor in students' growth and development is the teacher. Therefore in-service science teacher education to develop the professionality is important as well as the selection of new excellence teachers. Our research is on the development and application of new education program on science experiments where in-service teachers become the lecturers in the program and provide information that is bound to the context of real lessons. This program is consisted of following 10 steps of work, which was implemented in 5 months: sharing the philosophy of the program, selecting science experiments, first application of the experiments, discussion on the first application, learning how to edit the movie clips of the lesson, second application of the experiments, in depth discussion on the second application, developing the experiment package, giving lecture to other science teachers, and evaluating the program. We describe the process of the program developed and implemented in detail to suggest a model of science teacher education program on science experiments and discuss educational implications. This program is characterized by the emphasis of the context closely linked to the real lessons, the problem solving in a real situation, and the collaboration of teachers, professors and science education researcher in a teacher education.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.120-125
• /
• 2000

We propose a semi-automatic and dynamic indexing algorithm for multi-media database(e.g. movie files, audio files), which are difficult to create indexes expressing their emotional or abstract contents, according to user's sensitivity by using user's histories of access to database. In this algorithm, we simply categorize data at first, create a vector space of each user's interest(user model) from the history of which categories the data belong to, and create vector space of each data(title model) from the history of which users the data had been accessed from. By continuing the above method, we could create suitable indexes, which show emotional content of each data. In this paper, we define the recurrence formulas based on the proposed algorithm. We also show the effectiveness of the algorithm by simulation result.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4684-4705
• /
• 2019

Collaborative filtering recommender systems are vulnerable to shilling attacks in which malicious users may inject biased profiles to promote or demote a particular item being recommended. To tackle this problem, many robust collaborative recommendation methods have been presented. Unfortunately, the robustness of most methods is improved at the expense of prediction accuracy. In this paper, we construct a robust Bayesian probabilistic matrix factorization model for collaborative filtering recommender systems by incorporating the detection of user anomaly rating behaviors. We first detect the anomaly rating behaviors of users by the modified K-means algorithm and target item identification method to generate an indicator matrix of attack users. Then we incorporate the indicator matrix of attack users to construct a robust Bayesian probabilistic matrix factorization model and based on which a robust collaborative recommendation algorithm is devised. The experimental results on the MovieLens and Netflix datasets show that our model can significantly improve the robustness and recommendation accuracy compared with three baseline methods.